AI is a valuable tool that can help veterinarians do their jobs with greater speed and precision, freeing them up to focus on complex tasks and concentrate on patient welfare.
Artificial intelligence (AI) is fairly new to the animal health sector. Over the past decade, however, researchers, scientists, and entrepreneurs have begun to introduce machine learning and AI into veterinary health, with groundbreaking results.
AI is not always welcomed with open arms when it appears in an industry. People often have concerns. They worry that artificial intelligence will replace humans and remove jobs. However, this is not the case in veterinary science. When it comes to diagnosing and treating diseases in animals, nothing can replace the expertise of a good veterinarian. AI is a valuable, advanced tool that can help veterinarians do their jobs with greater speed and precision, freeing them up to focus on complex tasks and concentrate on the welfare of their patients.
How is AI being used in animal health?
The fact that AI is good at repetitive, data-centered, and often mind-numbing tasks that most humans aren’t equipped for means it has the potential to drastically change veterinary medicine. In fact, AI is already being used in various areas of the animal health industry to help veterinarians diagnose, treat, and make better decisions about animal health.
Animals always need x-rays, but unfortunately, there are not as many people to take and interpret those images. Recently, there haven’t been enough veterinary imaging professionals.¹ While teaching staff in universities have been hardest hit by the shortage, even lucrative private veterinary practices are struggling to find and keep veterinary radiologists. AI can fill the gap left by these shortages.
At least two startups are offering AI products that interpret x-ray images.² The computer software created by these companies uses AI to read x-rays and interpret them quickly and inexpensively. The software is cloud-based; users access it by signing into a website and uploading images. The results come back almost immediately so the veterinarian can move on with the process of diagnosis and treatment.
AI is extremely well suited to radiology because pictures really do contain a thousand words. X-rays are filled with data, and AI is able to quickly compare previous and current images, prioritize data, and analyze images. Veterinary radiologists are still needed to read complex images, but AI can streamline the analysis process, filtering out mundane and uninteresting x-rays so that human doctors can concentrate on the images that most need attention and the expertise of a trained clinician.
Thanks to continuous improvements in modern medicine, veterinarians are inundated with data from devices, software, and other sources. While more is certainly better, it can also be overwhelming; large datasets are difficult for humans to read. They also might contain irrelevant data or false patterns. Also, when faced with a firehose of data, a human being is likely to miss the big picture. Not so with AI, which never tires, and can sift through large quantities of data to find complex patterns, unprecedented correlations, or small abnormalities humans cannot see.
For example, consider some recent work done by veterinarians at the University of California, Davis School of Veterinary Medicine,³ who worked with a computer engineer to develop an algorithm tasked with finding Addison’s disease in dogs. Addison’s is a rare disorder, potentially fatal because it mimics the symptoms of other diseases. This means it’s often misdiagnosed, going undetected and untreated for years. Dogs with Addison’s present with vague symptoms that look like other conditions, such as kidney and intestinal disease.
Normally, when a sick patient first visits the vet, routine blood tests are ordered — a complete blood count and serum biochemical profile. Because Addison’s patients lack critical hormones, their tests often come back with subtle irregularities that are frequently confused with other conditions. The UC Davis team’s algorithm uses AI to analyze blood work data and detect complex patterns unique to Addison’s. The researchers used the test results of 1,000 dogs to train their algorithm to detect the patterns that signal Addison’s. The algorithm functions as an alert system, using information from routine screening tests to flag patients in which Addison’s disease is likely, and inform veterinarian that further investigation is necessary. It has been 99% effective in diagnosing new patients.
Diagnosis and prediction
When it comes to life-threatening diseases, it is critical to catch them before they develop. This may sound impossible, but with the right data, vets can make educated predictions about which animals will develop a disease. Chronic kidney disease (CKD) in cats is a good example — it’s not reversible, and often, by the time it presents, the patient has already suffered kidney damage. It’s also a disease that tends to affect older cats, so by the time a veterinarian catches a case o CKD, the cat’s quality of life is likely to be severely impacted. If the disease occurrence can be predicted, however, the patient can be treated before kidney damage occurs, and the cat’s health and quality of life can be dramatically improved.
Researchers recently developed an algorithm to predict CKD before a cat gets sick⁴. It uses AI to predict whether a cat will develop the disease. Trained on Electronic Health Records (EHR) from 20 years of vet visits, the algorithm looked for specific factors that contributed to CKD in more than 100,000 cats across breeds, geographical areas, and ranging in age from one year old to more than 22.
Using this dataset, the team built a recurrent neural network (RNN) that examines blood work for four factors contributing to CKD: creatinine, blood urea nitrogen, urine specific gravity, and age. The RNN was able to predict whether a cat will develop CKD within the next two years with greater than 95% accuracy. The false positives were very low — a huge benefit for vets and pet owners who have traditionally dealt with CKD as a difficult-to-detect disease. This model, say the researchers, can quickly be implemented in hospital practice or diagnostic laboratory software to directly support veterinarians in making clinical decisions regarding sick cats.
Prediction isn’t just about the disease; it’s also about treatment, because not all patients respond well to the same therapeutics. For instance, the treatment of blood cancers, the most common of canine cancers, can benefit from AI.
In general, chemotherapy is the most widely-used treatment option for canine blood cancers, but finding the right drugs for each patient can be a challenge for vets. A wait-and-see approach after drug administration to a patient’s body can be costly, time-consuming, and take a toll on the patient and the humans who love them. AI can help veterinarians find the most effective drugs for each individual patient and exclude ineffective ones before treatment even begins, often called a “precision medicine” approach.
One application of AI for cancer precision medicine involves the analysis of various drug responses using “live” tumor cells from canine lymphoma patients.⁵ This approach, in which researchers use fine-needle aspirates of cancer cells from the affected lymph nodes, uses AI to combine molecular, cellular, and clinical information in order to predict which anti-cancer drugs will work best for a specific dog’s particular lymphoma or leukemia. Researchers tested and analyzed the live tumor cells’ responses to commonly-prescribed chemotherapy drugs using various AI models, and predicted the drugs most likely to work on the patient. Once the prediction report is made to a veterinarian, he or she can design a course of individualized treatment for each patient.
The study found that patients who had been tested achieved clinical remission much more quickly with their selected drugs. Such precision medicine service enables veterinarians to recommend drugs or drug combinations that will help their patients, rather than taking a trial and error approach to chemotherapy.
AI’s role in the veterinary office
Veterinarians have always applied leading edge advances in technology to animal health: from digital imaging to sophisticated anesthesia, new technology has changed and improved veterinary medicine. So it’s no surprise that vets have begun turning to AI to improve the care and quality of life of their patients.
While AI is excellent at crunching numbers and digesting a large amount of data quickly, however, it doesn’t do well at some of the tasks at which humans excel. Creativity, problem solving without a defined training dataset, and of course, bedside manner, are all human skills that AI cannot duplicate. For this reason, AI is an excellent partner to veterinarians. By taking the pressure of diagnosis, prediction, or data analysis off a vet, AI allows vets to really focus on their patients’ health problems, decide on courses of treatments, and make sure an animal has the best quality of life possible.
1Kelly R. Artificial intelligence use rising in veterinary radiology. VIN News. https://news.vin.com/default.aspx?pid=210&Id=10118453. Published March 2, 2021. Accessed June 8, 2021.
2Cima G. Specialists in short supply. American Veterinary Medical Association. https://www.avma.org/javma-news/2018-10-15/specialists-short-supply. Published September 26, 2018. Accessed June 8, 2021.
3Warren R. Veterinarians Use Artificial Intelligence to Aid in the Diagnosis of Addison’s Disease. School of Veterinary Medicine. https://www.vetmed.ucdavis.edu/news/veterinarians-use-artificial-intelligence-aid-diagnosis-addisons-disease. Published December 5, 2020. Accessed June 8, 2021.
4Bradley R, Tagkopoulos I, Kim M, et al. Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning. J Vet Intern Med. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6872623/. Published September 26, 2019. Accessed June 8, 2021.
5Bohannan Z, Pudupakam RS, Koo J, et al. Predicting likelihood of in vivo chemotherapy response in canine lymphoma using ex vivo drug sensitivity and immunophenotyping data in a machine learning model. Wiley Online Library. https://onlinelibrary.wiley.com/doi/10.1111/vco.12656. Published October 20, 2020. Accessed June 8, 2021.